© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 45238
    Prev
    Next
    INDEX
    Explanations

    Reykjavik descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ãĺ
    -0.13
     Swedish
    -0.12
    Ãĺ
    -0.12
     Ãħ
    -0.12
     Norwegian
    -0.12
     Gor
    -0.11
     Ori
    -0.10
     Finnish
    -0.10
     Norway
    -0.10
     Scandinavian
    -0.10
    POSITIVE LOGITS
     Rey
    0.26
     Iceland
    0.19
    ð
    0.15
    Ãŀ
    0.15
     hver
    0.15
     Ey
    0.15
     þ
    0.14
     Grape
    0.14
     Icelandic
    0.14
     Ã
    0.14
    Activations Density 0.019%

    No Known Activations